SDXL 1.0 BASE ONLY, HIGLY RECOMENDED.

About: Trained on selected dataset of dalle-2 images, need the default model to work.

Default model: https://civarchive.com/models/101055/sd-xl?modelVersionId=128078

For Foocus, styles can improve your image look, more description is better.

❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️
Do and tips: 1 weight for generation / 1.2/1.5 weight for img2img

Keyword: oil painting and fantasy can bring back some esque for different models.